{"id":"https://openalex.org/W4414248029","doi":"https://doi.org/10.1145/3719545.3721107","title":"Logarithmic Function Matters Policy Gradient Deep Reinforcement Learning","display_name":"Logarithmic Function Matters Policy Gradient Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4414248029","doi":"https://doi.org/10.1145/3719545.3721107"},"language":"en","primary_location":{"id":"doi:10.1145/3719545.3721107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3719545.3721107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453223","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0002-7520-306X"},"institutions":[{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-7520-306X","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210142539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100316412","display_name":"Jingxiang Guo","orcid":"https://orcid.org/0009-0009-2314-6911"},"institutions":[{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxiang Guo","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0009-2314-6911","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210142539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075369343","display_name":"Zhongjian Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjian Qiao","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0007-4605-4468","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019552295","display_name":"Pengbin Chen","orcid":"https://orcid.org/0009-0007-4307-5618"},"institutions":[{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengbin Chen","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0007-4307-5618","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210142539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010910123","display_name":"Jinxuan Zhu","orcid":"https://orcid.org/0000-0002-7636-4586"},"institutions":[{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxuan Zhu","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-7636-4586","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210142539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-7890-9677","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210142539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100453223"],"corresponding_institution_ids":["https://openalex.org/I4210142539"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27954377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9211000204086304,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5059000253677368},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4952000081539154},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.3133000135421753},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3095000088214874},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.3061999976634979},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2919999957084656}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42480000853538513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40869998931884766},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3719545.3721107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3719545.3721107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2091565802","https://openalex.org/W2145339207","https://openalex.org/W2172968643","https://openalex.org/W2492794003","https://openalex.org/W2990138404","https://openalex.org/W3091937952","https://openalex.org/W4206173630","https://openalex.org/W4206268406","https://openalex.org/W4206314361","https://openalex.org/W4214717370","https://openalex.org/W4220880510","https://openalex.org/W4241811150","https://openalex.org/W4378190882","https://openalex.org/W4391774091","https://openalex.org/W4391774123","https://openalex.org/W4392667113"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}